tweak some timeouts so that we do trigger a banning even if the control hangs/timesout

diff --git a/server/ctdb_recoverd.c b/server/ctdb_recoverd.c
index c812f916959ffa72d261939e88b3a242a551efcc..2e460dd448ee89e0a44f3127882940340d1a1635 100644 (file)
--- a/server/ctdb_recoverd.c
+++ b/server/ctdb_recoverd.c
@@ -1346,9 +1346,9 @@ static int do_recovery(struct ctdb_recoverd *rec,
 
        if (rec->culprit_counter > 2*nodemap->num) {
                DEBUG(DEBUG_NOTICE,("Node %u has caused %u recoveries in %.0f seconds - banning it for %u seconds\n",
-                        culprit, rec->culprit_counter, timeval_elapsed(&rec->first_recover_time),
+                        rec->last_culprit, rec->culprit_counter, timeval_elapsed(&rec->first_recover_time),
                         ctdb->tunable.recovery_ban_period));
-               ctdb_ban_node(rec, culprit, ctdb->tunable.recovery_ban_period);
+               ctdb_ban_node(rec, rec->last_culprit, ctdb->tunable.recovery_ban_period);
        }
 
        if (!ctdb_recovery_lock(ctdb, true)) {

diff --git a/server/ctdb_tunables.c b/server/ctdb_tunables.c
index f758c2cf182644eb15caf255e91e96e7b89a8815..365865e860db5c61d7d8c36c0b251fb7fc8bac86 100644 (file)
--- a/server/ctdb_tunables.c
+++ b/server/ctdb_tunables.c
@@ -31,7 +31,7 @@ static const struct {
        { "KeepaliveInterval",    5,  offsetof(struct ctdb_tunable, keepalive_interval) },
        { "KeepaliveLimit",       5,  offsetof(struct ctdb_tunable, keepalive_limit) },
        { "MaxLACount",           7,  offsetof(struct ctdb_tunable, max_lacount) },
-       { "RecoverTimeout",      30,  offsetof(struct ctdb_tunable, recover_timeout) },
+       { "RecoverTimeout",      20,  offsetof(struct ctdb_tunable, recover_timeout) },
        { "RecoverInterval",      1,  offsetof(struct ctdb_tunable, recover_interval) },
        { "ElectionTimeout",      3,  offsetof(struct ctdb_tunable, election_timeout) },
        { "TakeoverTimeout",      5,  offsetof(struct ctdb_tunable, takeover_timeout) },
@@ -39,7 +39,7 @@ static const struct {
        { "TickleUpdateInterval",20,  offsetof(struct ctdb_tunable, tickle_update_interval) },
        { "EventScriptTimeout",  20,  offsetof(struct ctdb_tunable, script_timeout) },
        { "EventScriptBanCount",  5,  offsetof(struct ctdb_tunable, script_ban_count) },
-       { "RecoveryGracePeriod", 60,  offsetof(struct ctdb_tunable, recovery_grace_period) },
+       { "RecoveryGracePeriod", 120,  offsetof(struct ctdb_tunable, recovery_grace_period) },
        { "RecoveryBanPeriod",  300,  offsetof(struct ctdb_tunable, recovery_ban_period) },
        { "DatabaseHashSize", 10000,  offsetof(struct ctdb_tunable, database_hash_size) },
        { "DatabaseMaxDead",      5,  offsetof(struct ctdb_tunable, database_max_dead) },